- 08 Apr, 2019 1 commit
-
-
NeilBrown authored
nested_table_alloc() relies on the fact that there is at most one spinlock allocated for every slot in the top level nested table, so it is not possible for two threads to try to allocate the same table at the same time. This assumption is a little fragile (it is not explicit) and is unnecessary as cmpxchg() can be used instead. A future patch will replace the spinlocks by per-bucket bitlocks, and then we won't be able to protect the slot pointer with a spinlock. So replace rcu_assign_pointer() with cmpxchg() - which has equivalent barrier properties. If it the cmp fails, free the table that was just allocated. Signed-off-by:
NeilBrown <neilb@suse.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- 07 Apr, 2019 28 commits
-
-
David S. Miller authored
Murali Karicheri says: ==================== net: hsr: improvements and bug fixes This series has some coding style fixes and other bug fixes. Patch 12/14, I have also done SPDX conversion. Not sure if that is the only thing needed and is correct. So please pay close attention to this patch before merge as I would like to avoid any issue related to licensing applicable for this code. ==================== Signed-off-by: -
Aaron Kramer authored
HSR should forget nodes after configured node forget time expiry based on HSR_NODE_FORGET_TIME. As part of hsr_prune_nodes(), code checks to see if entries are to be flushed out if not heard for longer than forget time. But currently hsr_prune_nodes() is called only once during device creation. Restart the timer at the end of hsr_prune_nodes() so that hsr_prune_nodes() gets called periodically and forgotten entries are removed from node table. Signed-off-by:
Aaron Kramer <a-kramer@ti.com> Signed-off-by:
Murali Karicheri <m-karicheri2@ti.com> Signed-off-by:
-
Murali Karicheri authored
This adds a debugfs interface to allow display the nodes learned by the hsr master. Signed-off-by:
-
Murali Karicheri authored
Use SPDX-License-Identifier instead of a verbose license text. Signed-off-by:
-
Murali Karicheri authored
Add a blank line after function declaration as suggested by checkpatch.pl -f Signed-off-by:
-
Murali Karicheri authored
Current driver code uses camel case in many places. This is seen when ran checkpatch.pl -f on files under net/hsr. This patch fixes the code to remove camel case usage. Signed-off-by:
-
Murali Karicheri authored
This patch add missing space around operator in code. This is seen when ran checkpatch.pl -f on files under net/hsr. Signed-off-by:
-
Murali Karicheri authored
In a multi-line statement exceeding 80 characters, logical operator should be at the end of a line instead of being at the start. This is seen when ran checkpatch.pl -f on files under net/hsr. The change is per suggestion from checkpatch. Signed-off-by:
-
Murali Karicheri authored
This patch removes unnecessary space after a cast. This is seen when ran checkpatch.pl -f on files under net/hsr. Signed-off-by:
-
Murali Karicheri authored
This patch replaces all instance of NULL checks such as if (foo == NULL) with if (!foo) Also if (foo != NULL) with if (foo) This is seen when ran checkpatch.pl -f on files under net/hsr and suggestion is to replace as above. Signed-off-by: -
Murali Karicheri authored
This patch fixes function calls that ends with '(' in a line. This is seen when ran checkpatch.pl -f option on files under net/hsr. Signed-off-by: -
Murali Karicheri authored
This patch fixes alignment issues in code for functions. This is seen when ran checkpatch.pl -f option on files under net/hsr. Signed-off-by:
-
Murali Karicheri authored
This patch fixes unnecessary paranthesis from the code. This is seen when ran checkpatch.pl -f option on files under net/hsr. Signed-off-by:
-
Murali Karicheri authored
This patch fixes multiple blank lines in the code. This is seen when ran checkpatch.pl -f option for files under net/hsr Signed-off-by:
-
Murali Karicheri authored
This patch fixes lines exceeding 80 characters. This is seen when ran checkpatch.pl with -f option for files under net/hsr. Signed-off-by:
-
Nikolay Aleksandrov authored
This test is split in two, the first part checks if a report creates a corresponding mdb entry and if traffic is properly forwarded to it, and the second part checks if the mdb entry is deleted after a leave and if traffic is *not* forwarded to it. Since the mcast querier is enabled we should see standard mcast snooping bridge behaviour. Signed-off-by:
Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by:
-
Colin Ian King authored
Currently mskid is unsigned and hence comparisons with negative error return values are always false. Fix this by making mskid an int. Fixes: f058e468 ("net: hns: fix ICMP6 neighbor solicitation messages discard problem") Addresses-Coverity: ("Operands don't affect result") Signed-off-by:
Colin Ian King <colin.king@canonical.com> Reviewed-by:
Mukesh Ojha <mojha@codeaurora.org> Signed-off-by:
-
David S. Miller authored
Mario Limonciello says: ==================== r8152: Support runtime changes of vendor mac passthu policy On some platforms ACPI method `\\_SB.AMAC` is dynamic and changes to it can influence changing the behavior of MAC pass through and what MAC address is used. When running USB reset, re-read the MAC address to use to support tools that change the policy. This is quite similar to using `SIOCSIFHWADDR` except that the actual MAC to use comes from ASL rather than from userspace. Changes from v1: * Remove an extra unneeded `ether_addr_copy` call * Use `dev_set_mac_address` to ensure all notifiers are called * Shuffle functions to allow code re-use. ==================== Signed-off-by: -
Mario Limonciello authored
On some platforms it is possible to dynamically change the policy of what MAC address is selected from the ASL at runtime. These tools will reset the USB device and expect the change to be made immediately. Signed-off-by:
Mario Limonciello <mario.limonciello@dell.com> Signed-off-by:
-
Mario Limonciello authored
This already happens later on in `rtl8152_set_mac_address` Signed-off-by:
-
Colin Ian King authored
The non-null check on tskb is always false because it is in an else path of a check on tskb and hence tskb is null in this code block. This is check is therefore redundant and can be removed as well as the label coalesc. if (tsbk) { ... } else { ... if (unlikely(!skb)) { if (tskb) /* can never be true, redundant code */ goto coalesc; return; } } Addresses-Coverity: ("Logically dead code") Signed-off-by:Eric Dumazet <edumazet@google.com> Signed-off-by:
-
David S. Miller authored
Jerome Brunet says: ==================== net: phy: add Amlogic g12a support This patchset adds the necessary bits to support network on the Amlogic g12a SoC family. Only the internal PHY and related MDIO mux needed to be addressed. The GMAC remains compatible with axg SoC family This series has been tested on the u200 (S905D2) with both the internal and external (Realtek) PHYs. Change since v2 [1]: * Change 'clk part' Reviewed-by as suggested * Remove default callback from phy drivers * Use exact match PHY macros * Default MDIO g12a as module if ARCH_MESON is enabled * Don't print error on probe defer in the g12a mdio mux Change since v1 [0]: * drop '_' from function name unrelated to locking * fix peripheral clock disable on error * fix variable declaration reverse Xmas trees * fix Kconfig dependency on CCF (Actually needed for 'struct clk_hw', Thx Andrew !) * Minor fix in the DT exemple as reported by Rob [0] https://lkml.kernel.org/r/20190314140135.19184-1-jbrunet@baylibre.com [1] https://lkml.kernel.org/r/20190329141512.29867-1-jbrunet@baylibre.com ==================== Signed-off-by:
-
Jerome Brunet authored
The purpose of this change is to align the gxl and g12a driver declaration. Like on the g12a variant, remove genphy_aneg_done() from the driver declaration as the net phy framework will default to it anyway. Also, the gxl phy id should be an exact match as well, so let's change this and use the macro provided. Signed-off-by:
Jerome Brunet <jbrunet@baylibre.com> Reviewed-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Jerome Brunet authored
The g12a SoC family uses the type of internal PHY that was used on the gxl family. The quirks of gxl family, like the LPA register corruption, appear to have been resolved on this new SoC generation. Signed-off-by:
-
Jerome Brunet authored
Add support for the mdio mux and internal phy glue of the g12a SoC family Reviewed-by: Neil Armstrong <narmstrong@baylibre.com> # clk parts Signed-off-by:
-
Jerome Brunet authored
Add documentation for the device tree bindings of the MDIO mux of Amlogic g12a SoC family Reviewed-by:
Rob Herring <robh@kernel.org> Signed-off-by:
-
Yuval Shaia authored
Signed-off-by:
Yuval Shaia <yuval.shaia@oracle.com> Signed-off-by:
-
Yuval Shaia authored
This header is not in use - remove it. Signed-off-by:
-
- 06 Apr, 2019 1 commit
-
-
Heiner Kallweit authored
In contrast to switching rx irq coalescing off what fixed an issue, switching tx irq coalescing off is merely a latency optimization, therefore net-next. As part of this change: - Remove INTT_0 .. INTT_3 constants, they aren't used. - Remove comment in rtl_hw_start_8169(), we now have a detailed description by the code in rtl_set_coalesce(). - Due to switching irq coalescing off per default we don't need the initialization in rtl_hw_start_8168(). If ethtool is used to switch on coalescing then rtl_set_coalesce() will configure this register. For the sake of completeness: This patch just changes the default. Users still have the option to configure irq coalescing via ethtool. Signed-off-by:
Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by:
-
- 05 Apr, 2019 10 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller authored
Minor comment merge conflict in mlx5. Staging driver has a fixup due to the skb->xmit_more changes in 'net-next', but was removed in 'net'. Signed-off-by: -
git://git.kernel.org/pub/scm/linux/kernel/git/mel/linuxLinus Torvalds authored
Pull mm/compaction fixes from Mel Gorman: "The merge window for 5.1 introduced a number of compaction-related patches. with intermittent reports of corruption and functional issues. The bugs are due to sloopy checking of zone boundaries and a corner case where invalid indexes are used to access the free lists. Reports are not common but at least two users and 0-day have tripped over them. There is a chance that one of the syzbot reports are related but it has not been confirmed properly. The normal submission path is with Andrew but there have been some delays and I consider them urgent enough that they should be picked up before RC4 to avoid duplicate reports. All of these have been successfully tested on older RC windows. This will make this branch look like a rebase but in fact, they've simply been lifted again from Andrew's tree and placed on a fresh branch. I've no reason to believe that this has invalidated the testing given the lack of change in compaction and the nature of the fixes" * tag 'mm-compaction-5.1-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux: mm/compaction.c: abort search if isolation fails mm/compaction.c: correct zone boundary handling when resetting pageblock skip hints
-
Greg Kroah-Hartman authored
The n_r3964 line discipline driver was written in a different time, when SMP machines were rare, and users were trusted to do the right thing. Since then, the world has moved on but not this code, it has stayed rooted in the past with its lovely hand-crafted list structures and loads of "interesting" race conditions all over the place. After attempting to clean up most of the issues, I just gave up and am now marking the driver as BROKEN so that hopefully someone who has this hardware will show up out of the woodwork (I know you are out there!) and will help with debugging a raft of changes that I had laying around for the code, but was too afraid to commit as odds are they would break things. Many thanks to Jann and Linus for pointing out the initial problems in this codebase, as well as many reviews of my attempts to fix the issues. It was a case of whack-a-mole, and as you can see, the mole won. Reported-by:
Jann Horn <jannh@google.com> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
git://anongit.freedesktop.org/drm/drmLinus Torvalds authored
Pull drm fixes from Dave Airlie: "Pretty quiet week, just some amdgpu and i915 fixes. i915: - deadlock fix - gvt fixes amdgpu: - PCIE dpm feature fix - Powerplay fixes" * tag 'drm-fixes-2019-04-05' of git://anongit.freedesktop.org/drm/drm: drm/i915/gvt: Fix kerneldoc typo for intel_vgpu_emulate_hotplug drm/i915/gvt: Correct the calculation of plane size drm/amdgpu: remove unnecessary rlc reset function on gfx9 drm/i915: Always backoff after a drm_modeset_lock() deadlock drm/i915/gvt: do not let pin count of shadow mm go negative drm/i915/gvt: do not deliver a workload if its creation fails drm/amd/display: VBIOS can't be light up HDMI when restart system drm/amd/powerplay: fix possible hang with 3+ 4K monitors drm/amd/powerplay: correct data type to avoid overflow drm/amd/powerplay: add ECC feature bit drm/amd/amdgpu: fix PCIe dpm feature issue (v3)
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/netLinus Torvalds authored
Pull networking fixes from David Miller: 1) Several hash table refcount fixes in batman-adv, from Sven Eckelmann. 2) Use after free in bpf_evict_inode(), from Daniel Borkmann. 3) Fix mdio bus registration in ixgbe, from Ivan Vecera. 4) Unbounded loop in __skb_try_recv_datagram(), from Paolo Abeni. 5) ila rhashtable corruption fix from Herbert Xu. 6) Don't allow upper-devices to be added to vrf devices, from Sabrina Dubroca. 7) Add qmi_wwan device ID for Olicard 600, from Bjørn Mork. 8) Don't leave skb->next poisoned in __netif_receive_skb_list_ptype, from Alexander Lobakin. 9) Missing IDR checks in mlx5 driver, from Aditya Pakki. 10) Fix false connection termination in ktls, from Jakub Kicinski. 11) Work around some ASPM issues with r8169 by disabling rx interrupt coalescing on certain chips. From Heiner Kallweit. 12) Properly use per-cpu qstat values on NOLOCK qdiscs, from Paolo Abeni. 13) Fully initialize sockaddr_in structures in SCTP, from Xin Long. 14) Various BPF flow dissector fixes from Stanislav Fomichev. 15) Divide by zero in act_sample, from Davide Caratti. 16) Fix bridging multicast regression introduced by rhashtable conversion, from Nikolay Aleksandrov. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (106 commits) ibmvnic: Fix completion structure initialization ipv6: sit: reset ip header pointer in ipip6_rcv net: bridge: always clear mcast matching struct on reports and leaves libcxgb: fix incorrect ppmax calculation vlan: conditional inclusion of FCoE hooks to match netdevice.h and bnx2x sch_cake: Make sure we can write the IP header before changing DSCP bits sch_cake: Use tc_skb_protocol() helper for getting packet protocol tcp: Ensure DCTCP reacts to losses net/sched: act_sample: fix divide by zero in the traffic path net: thunderx: fix NULL pointer dereference in nicvf_open/nicvf_stop net: hns: Fix sparse: some warnings in HNS drivers net: hns: Fix WARNING when remove HNS driver with SMMU enabled net: hns: fix ICMP6 neighbor solicitation messages discard problem net: hns: Fix probabilistic memory overwrite when HNS driver initialized net: hns: Use NAPI_POLL_WEIGHT for hns driver net: hns: fix KASAN: use-after-free in hns_nic_net_xmit_hw() flow_dissector: rst'ify documentation ipv6: Fix dangling pointer when ipv6 fragment net-gro: Fix GRO flush when receiving a GSO packet. flow_dissector: document BPF flow dissector environment ... -
Thomas Falcon authored
Fix device initialization completion handling for vNIC adapters. Initialize the completion structure on probe and reinitialize when needed. This also fixes a race condition during kdump where the driver can attempt to access the completion struct before it is initialized: Unable to handle kernel paging request for data at address 0x00000000 Faulting instruction address: 0xc0000000081acbe0 Oops: Kernel access of bad area, sig: 11 [#1] LE SMP NR_CPUS=2048 NUMA pSeries Modules linked in: ibmvnic(+) ibmveth sunrpc overlay squashfs loop CPU: 19 PID: 301 Comm: systemd-udevd Not tainted 4.18.0-64.el8.ppc64le #1 NIP: c0000000081acbe0 LR: c0000000081ad964 CTR: c0000000081ad900 REGS: c000000027f3f990 TRAP: 0300 Not tainted (4.18.0-64.el8.ppc64le) MSR: 800000010280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE,TM[E]> CR: 28228288 XER: 00000006 CFAR: c000000008008934 DAR: 0000000000000000 DSISR: 40000000 IRQMASK: 1 GPR00: c0000000081ad964 c000000027f3fc10 c0000000095b5800 c0000000221b4e58 GPR04: 0000000000000003 0000000000000001 000049a086918581 00000000000000d4 GPR08: 0000000000000007 0000000000000000 ffffffffffffffe8 d0000000014dde28 GPR12: c0000000081ad900 c000000009a00c00 0000000000000001 0000000000000100 GPR16: 0000000000000038 0000000000000007 c0000000095e2230 0000000000000006 GPR20: 0000000000400140 0000000000000001 c00000000910c880 0000000000000000 GPR24: 0000000000000000 0000000000000006 0000000000000000 0000000000000003 GPR28: 0000000000000001 0000000000000001 c0000000221b4e60 c0000000221b4e58 NIP [c0000000081acbe0] __wake_up_locked+0x50/0x100 LR [c0000000081ad964] complete+0x64/0xa0 Call Trace: [c000000027f3fc10] [c000000027f3fc60] 0xc000000027f3fc60 (unreliable) [c000000027f3fc60] [c0000000081ad964] complete+0x64/0xa0 [c000000027f3fca0] [d0000000014dad58] ibmvnic_handle_crq+0xce0/0x1160 [ibmvnic] [c000000027f3fd50] [d0000000014db270] ibmvnic_tasklet+0x98/0x130 [ibmvnic] [c000000027f3fda0] [c00000000813f334] tasklet_action_common.isra.3+0xc4/0x1a0 [c000000027f3fe00] [c000000008cd13f4] __do_softirq+0x164/0x400 [c000000027f3fef0] [c00000000813ed64] irq_exit+0x184/0x1c0 [c000000027f3ff20] [c0000000080188e8] __do_irq+0xb8/0x210 [c000000027f3ff90] [c00000000802d0a4] call_do_irq+0x14/0x24 [c000000026a5b010] [c000000008018adc] do_IRQ+0x9c/0x130 [c000000026a5b060] [c000000008008ce4] hardware_interrupt_common+0x114/0x120 Signed-off-by:
Thomas Falcon <tlfalcon@linux.ibm.com> Signed-off-by:
-
Lorenzo Bianconi authored
ipip6 tunnels run iptunnel_pull_header on received skbs. This can determine the following use-after-free accessing iph pointer since the packet will be 'uncloned' running pskb_expand_head if it is a cloned gso skb (e.g if the packet has been sent though a veth device) [ 706.369655] BUG: KASAN: use-after-free in ipip6_rcv+0x1678/0x16e0 [sit] [ 706.449056] Read of size 1 at addr ffffe01b6bd855f5 by task ksoftirqd/1/= [ 706.669494] Hardware name: HPE ProLiant m400 Server/ProLiant m400 Server, BIOS U02 08/19/2016 [ 706.771839] Call trace: [ 706.801159] dump_backtrace+0x0/0x2f8 [ 706.845079] show_stack+0x24/0x30 [ 706.884833] dump_stack+0xe0/0x11c [ 706.925629] print_address_description+0x68/0x260 [ 706.982070] kasan_report+0x178/0x340 [ 707.025995] __asan_report_load1_noabort+0x30/0x40 [ 707.083481] ipip6_rcv+0x1678/0x16e0 [sit] [ 707.132623] tunnel64_rcv+0xd4/0x200 [tunnel4] [ 707.185940] ip_local_deliver_finish+0x3b8/0x988 [ 707.241338] ip_local_deliver+0x144/0x470 [ 707.289436] ip_rcv_finish+0x43c/0x14b0 [ 707.335447] ip_rcv+0x628/0x1138 [ 707.374151] __netif_receive_skb_core+0x1670/0x2600 [ 707.432680] __netif_receive_skb+0x28/0x190 [ 707.482859] process_backlog+0x1d0/0x610 [ 707.529913] net_rx_action+0x37c/0xf68 [ 707.574882] __do_softirq+0x288/0x1018 [ 707.619852] run_ksoftirqd+0x70/0xa8 [ 707.662734] smpboot_thread_fn+0x3a4/0x9e8 [ 707.711875] kthread+0x2c8/0x350 [ 707.750583] ret_from_fork+0x10/0x18 [ 707.811302] Allocated by task 16982: [ 707.854182] kasan_kmalloc.part.1+0x40/0x108 [ 707.905405] kasan_kmalloc+0xb4/0xc8 [ 707.948291] kasan_slab_alloc+0x14/0x20 [ 707.994309] __kmalloc_node_track_caller+0x158/0x5e0 [ 708.053902] __kmalloc_reserve.isra.8+0x54/0xe0 [ 708.108280] __alloc_skb+0xd8/0x400 [ 708.150139] sk_stream_alloc_skb+0xa4/0x638 [ 708.200346] tcp_sendmsg_locked+0x818/0x2b90 [ 708.251581] tcp_sendmsg+0x40/0x60 [ 708.292376] inet_sendmsg+0xf0/0x520 [ 708.335259] sock_sendmsg+0xac/0xf8 [ 708.377096] sock_write_iter+0x1c0/0x2c0 [ 708.424154] new_sync_write+0x358/0x4a8 [ 708.470162] __vfs_write+0xc4/0xf8 [ 708.510950] vfs_write+0x12c/0x3d0 [ 708.551739] ksys_write+0xcc/0x178 [ 708.592533] __arm64_sys_write+0x70/0xa0 [ 708.639593] el0_svc_handler+0x13c/0x298 [ 708.686646] el0_svc+0x8/0xc [ 708.739019] Freed by task 17: [ 708.774597] __kasan_slab_free+0x114/0x228 [ 708.823736] kasan_slab_free+0x10/0x18 [ 708.868703] kfree+0x100/0x3d8 [ 708.905320] skb_free_head+0x7c/0x98 [ 708.948204] skb_release_data+0x320/0x490 [ 708.996301] pskb_expand_head+0x60c/0x970 [ 709.044399] __iptunnel_pull_header+0x3b8/0x5d0 [ 709.098770] ipip6_rcv+0x41c/0x16e0 [sit] [ 709.146873] tunnel64_rcv+0xd4/0x200 [tunnel4] [ 709.200195] ip_local_deliver_finish+0x3b8/0x988 [ 709.255596] ip_local_deliver+0x144/0x470 [ 709.303692] ip_rcv_finish+0x43c/0x14b0 [ 709.349705] ip_rcv+0x628/0x1138 [ 709.388413] __netif_receive_skb_core+0x1670/0x2600 [ 709.446943] __netif_receive_skb+0x28/0x190 [ 709.497120] process_backlog+0x1d0/0x610 [ 709.544169] net_rx_action+0x37c/0xf68 [ 709.589131] __do_softirq+0x288/0x1018 [ 709.651938] The buggy address belongs to the object at ffffe01b6bd85580 which belongs to the cache kmalloc-1024 of size 1024 [ 709.804356] The buggy address is located 117 bytes inside of 1024-byte region [ffffe01b6bd85580, ffffe01b6bd85980) [ 709.946340] The buggy address belongs to the page: [ 710.003824] page:ffff7ff806daf600 count:1 mapcount:0 mapping:ffffe01c4001f600 index:0x0 [ 710.099914] flags: 0xfffff8000000100(slab) [ 710.149059] raw: 0fffff8000000100 dead000000000100 dead000000000200 ffffe01c4001f600 [ 710.242011] raw: 0000000000000000 0000000000380038 00000001ffffffff 0000000000000000 [ 710.334966] page dumped because: kasan: bad access detected Fix it resetting iph pointer after iptunnel_pull_header Fixes: a09a4c8d ("tunnels: Remove encapsulation offloads on decap") Tested-by:Jianlin Shi <jishi@redhat.com> Signed-off-by:
Lorenzo Bianconi <lorenzo.bianconi@redhat.com> Signed-off-by:
-
David S. Miller authored
Tuong Lien says: ==================== tipc: improve TIPC unicast link throughput The series introduces an algorithm to improve TIPC throughput especially in terms of packet loss, also tries to reduce packet duplication due to overactive NACK sending mechanism. The link failover situation is also covered by the patches. ==================== Signed-off-by: -
Tuong Lien authored
In commit 0ae955e2656d ("tipc: improve TIPC throughput by Gap ACK blocks"), we enhance the link transmq by releasing as many packets as possible with the multi-ACKs from peer node. This also means the queue is now non-linear and the peer link deferdq becomes vital. Whereas, in the case of link failover, all messages in the link transmq need to be transmitted as tunnel messages in such a way that message sequentiality and cardinality per sender is preserved. This requires us to maintain the link deferdq somehow, so that when the tunnel messages arrive, the inner user messages along with the ones in the deferdq will be delivered to upper layer correctly. The commit accomplishes this by defining a new queue in the TIPC link structure to hold the old link deferdq when link failover happens and process it upon receipt of tunnel messages. Also, in the case of link syncing, the link deferdq will not be purged to avoid unnecessary retransmissions that in the worst case will fail because the packets might have been freed on the sending side. Acked-by:Ying Xue <ying.xue@windriver.com> Acked-by:
Jon Maloy <jon.maloy@ericsson.com> Signed-off-by:
Tuong Lien <tuong.t.lien@dektech.com.au> Signed-off-by:
-
Tuong Lien authored
For unicast transmission, the current NACK sending althorithm is over- active that forces the sending side to retransmit a packet that is not really lost but just arrived at the receiving side with some delay, or even retransmit same packets that have already been retransmitted before. As a result, many duplicates are observed also under normal condition, ie. without packet loss. One example case is: node1 transmits 1 2 3 4 10 5 6 7 8 9, when node2 receives packet #10, it puts into the deferdq. When the packet #5 comes it sends NACK with gap [6 - 9]. However, shortly after that, when packet #6 arrives, it pulls out packet #10 from the deferfq, but it is still out of order, so it makes another NACK with gap [7 - 9] and so on ... Finally, node1 has to retransmit the packets 5 6 7 8 9 a number of times, but in fact all the packets are not lost at all, so duplicates! This commit reduces duplicates by changing the condition to send NACK, also restricting the retransmissions on individual packets via a timer of about 1ms. However, it also needs to say that too tricky condition for NACKs or too long timeout value for retransmissions will result in performance reducing! The criterias in this commit are found to be effective for both the requirements to reduce duplicates but not affect performance. The tipc_link_rcv() is also improved to only dequeue skb from the link deferdq if it is expected (ie. its seqno <= rcv_nxt). Acked-by:
-
